Arnoud Visser

University of Amsterdam | UVA · Institute of Informatics

In this work, we study neural network architectures that will reduce the number of infractions made by autonomous-driving agents. These agents control vehicles by providing future waypoints directly from a forward-facing camera. Building on top of the teacher-student approach of Cheating by Segmentation, we investigate the impact of Pyramid Pooling...

We train a small Nvidia AI JetRacer to follow the road on a small DuckieTown highway. In the real-world, roads do not always have the same appearance, so the system should not be trained on lane markings alone but on the complete view of the front camera. To make this possible, the system is trained in simulation using a recent reinforcement learni...

Vehicles can follow roads based on a forward-looking camera, but this has to be done reliably in all circumstances. In daily traffic, they can encounter many unforeseen situations. Training for those situations in simulations should prepare them for such encounters, but this requires simulated worlds with enough complexity. In this paper, we compar...

This review explores a natural learning curve which gives an appropriate RoboCup Rescue challenge at the right age. Children who got involved in the age group 14+ should continue their learning experience until they reach graduate level. To reduce the cost of such a learning experience, simulation is an attractive option in a large part of the worl...

The challenge of the Rescue Simulation League is for a team of robots or agents to learn an optimal response to mitigate the effects of natural disasters. To operate optimally, several problems have to be jointly solved like task allocation, path planning, and coalition formation. Solve these difficult problems can be quite overwhelming for newcome...

This paper is aimed to provide a bridge from the RoboCup Junior to the RoboCup Rescue Simulation League. The intent of building the bridge would be to have a gradual increase in the complexity. This paper provides a ‘game field’ version of the rescue simulation competition suitable for students at different points along the learning curve.

This paper is aimed to provide a bridge from the RoboCup Junior to the RoboCup Rescue Simulation League. The intent of building the bridge would be to have a gradual increase in the complexity. This paper provides a 'game field' version of the rescue simulation competition suitable for students at different points along the learning curve.

This paper is aimed to provide a bridge from the RoboCup Junior to the RoboCup Rescue Simulation League. The intent of building the bridge would be to have a gradual increase in the complexity. This paper provides a ‘game field’ version of the rescue simulation competition suitable for students at different points along the learning curve.

Understanding how the visual cortex of the human brain really works is still an open problem for science today. A better understanding of natural intelligence could also benefit object-recognition algorithms based on convolutional neural networks. In this paper we demonstrate the asset of using a shallow residual neural network for this task. The b...

After a disaster a team of robots, must explore the devastated area. In the Major League, robots have to cooperate as a team, in the Junior League a single robot (one of the red and one of the blue team) has to find its way through the environment.

As there is a gap between RoboCup Junior and Virtual Rescue League, there is a rising demand on adding a new step in this bridge. This step should be a cost effective one, with a low barrier to entry, and designed for secondary students and undergrads to provide more educational benefits. Due to the increase in specialism this step could be designe...

• Provide a reliable simulation environment to study today tomorrow’s Urban Search and Rescue (USAR) challenges. • Promote: • Research in cooperative robotics with large heterogeneous teams • Research in distributed sensing and information fusion • Research in human-robot interfaces • Realistic and affordable benchmarking of successful multi-robot...

The purpose of this competition is to provide a common benchmark to demonstrate scientific progress in the application of robotics to Urban Search and Rescue. The rules of this competition are loosely inspired by the rules of the RoboCup Rescue Robot League and of the Agent Competition of the RoboCup Rescue Simulation League. As in the Rescue Robot...

The RoboCup Rescue competitions have been initiated in 2000. To celebrate 16 years of research and development in this socially relevant initiative this article gives an overview of the experience gained during these competitions. This article provides an overview the state-of-the-art and the lessons learned from the RoboCup Rescue competitions.

Supporting humans in the kitchen is a difficult task for a humanoid robot. This study focuses on one of the tasks identified in the HUMABOT Challenge, finding a tomato in a kitchen environment and grabbing it from the table. Three detection algorithms are evaluated on their performance to find the tomato without confusion with other vegetables pres...

Since the first demonstration of the Virtual Robot Competition, USARSim has been used as the simulation interface and environment. The underlying simulation platform, Unreal Engine, has seen three major upgrades (UT2004, UT3 and UDK). These upgrades required a whole new USARSim simulator to be built from scratch. Yet, between those versions the USA...

This paper describes MRESim, a multi-robot exploration simulator which aims to provide a middle ground between the RoboCup Agent and Virtual Robot competitions. A detailed description of this new infrastructure is provided, followed by examples and case studies of successful research outcomes arising from the use of MRESim. Our work on MRESim won t...

For Micro Aerial Vehicles (MAVs), robust ob-stacle avoidance during flight is a challenging problem because only light weight sensors as monocular cameras can be mounted as pay-load. With monocular cameras depth percep-tion cannot be estimated from a single view, which means that information has to be esti-mated by combining images from multiple vi...

The RoboCup rescue simulation competitions have been held since 2001. The experience gained during these competitions has sup-ported the development of multi-agent and robotics based solution for disaster mitigation. The league consists of three distinct competitions. These competitions are the agent competition, the virtual robots com-petition, an...

This book includes the thoroughly refereed post-conference proceedings of the 17th Annual RoboCup International Symposium, held in Eindhoven, The Netherlands, in June 2013. The 20 revised papers presented together with 11 champion team papers, 3 best paper awards, 11 oral presentations, and 19 special track on open-source hard- and software papers...

In contrast to human soccer players, autonomous robot soccer players often move according to a limited set of predefined behavioral rules. This knowledge can be used advantageously: If the opponent’s behavioral rules are learned, it will be possible to detect these during a match and react accordingly. A method for autonomous activity mining in vid...

In this paper an extension of the model-based visual compass is presented, which can be updated continuously, allowing a robot to orient itself in a changing environment. To build a model, colors in the image are discretized to an automatically generated color profile, and transitions between these classes within vertical lines are used as feature....

This paper describes a framework for optimizing walking parameters for a Nao humanoid robot. In this case an omnidirectional walk is learned. The parameters are learned in simulation with an evolutionary approach. The best performance was obtained for a combination of a low mutation rate and a high crossover rate.

The Robot Operating System (ROS) has been steadily gaining popularity among robotics researchers as an open source framework for robot control. The Unified System for Automation and Robot Simulation (USARSim) has been used for many years by robotics researchers and developers as a validated framework for simulation. This paper presents a new ROS no...

RoboCup 2013 Symposium

Inside the RoboCup Rescue Simulation League, the mission is to use robots to rescue as many victims as possible after a disaster. The research challenge is to let the robots cooperate as a team. This year in total 15 teams from 8 different countries have been active in the competition. This paper highlights the approaches of the winners of the virt...

The RoboCup is an initiative to promote the development of robotics in a social relevant way. The competition consists of several leagues and it would be bene�cial if developments in one league could be reused in other leagues. This paper describes the development of a simulation model for a humanoid robot inside USARSim, which could be the basis o...

One of the main requirements in enabling autonomous flight of Micro Aerial Vehicles is the ability of autonomous navigation. One possible solution to solve this navigation problem is to use vision-based line-following algorithms. Such vision-based algorithm could rely on the various linear structures, which are present in the human constructed envi...

This paper gives a description of an approach to analyze the sensor information of the surroundings to select places where the foot of a humanoid can be placed. This will allow apply such robot in a rescue scenario, as foreseen in the DARPA Robotics Challenge, where a robot is forced to traverse difficult terrain.

The RoboCup Rescue Robot and Simulation competitions have been held since 2000. The experience gained during these competitions has increased the maturity level of the field, which allowed deploying robots after real disasters (for example, the Fukushima Daiichi nuclear disaster). This article provides an overview of these competitions and highligh...

In this paper time-augmented Petri nets are used to model people in the transit hall of an airport. Their behavior is strongly influenced by an event with a clear deadline (their flight), but typically there is so much time left that they linger and can be tempted to show random other behaviors, often induced by the location (encountering a coffee...

The developments in unmanned aerial vehicles make it possible to use this platform on a much larger scale. The current challenge is to use a team of flying robots to explore a city block, place lookouts at strategic points and if possible to enter some of the buildings in the block, to search for hazards and/or people. This challenge is still quite...

This paper describes a model to replicate the dynamics of a walking robot inside USARSim. USARSim is an existing 3D simulator based on the Unreal Engine, which provides facilities for good quality rendering, physics simulation, networking, a highly versatile scripting language and a powerful visual editor. To model the dynamics of a walking robot t...

This article describes a method to develop a generic approach to acquire navigation capabilities for the standard platform of the IMAV indoor competition: the Parrot AR. Drone. Our development is partly based on simulation, which requires both a realistic sensor and motion model. The AR. Drone simulation model is described and validated. Furthermor...

Following a soccer game is an example where clear emotions are displayed. This example is worked out for a humanoid robot which can express emotions with body language. The emotions expressed by the robot are not just stimuli-response, but are based on an affective state which shows dynamic behavior during the game. This can be live demonstrated wi...

In the near future, groups of autonomous robots using wireless communication will be used for a wide variety of tasks. In many such applications, communication may be unreliable and communication ranges difficult to predict. While most current approaches to this problem strive to keep team members within range of one another, we propose an approach...

This chapter gives an overview of the state of the art in decision-theoretic models to describe cooperation between multiple agents in a dynamic environment. Making (near-) optimal decisions in such settings gets harder when the number of agents grows or the uncertainty about the environment increases. It is essential to have compact models, becaus...

This is the debut of the Dutch Nao Team in the Standard Platform League. The team is a recreation of the Dutch Aibo Team, which was active in the predecessor of the SPL (2004-2006). This year participation is mainly intended to gain experience. As basis for the competition the code release of B-Human is used, with two modifications. The first modif...

The Urban Search and Rescue Simulation used for RoboCup lacks realistic response of laser range finders on smoke. In this paper, the behavior of a Hokuyo and Sick laser range finder in a smoky environment is studied. The behavior of the lasers is among others a function of the visibility level, and in this article this function is quantified into a...

For many robotics applications (such as robotic search and rescue), information about the environment must be gathered by a team of robots and returned to a single, specific location. Coordination of robots and sharing of information is vital, and when environments have severe communication limitations, approaches must be robust to communication dr...

Urban Search And Rescue is a growing area of robotic research. The RoboCup Federation has recognized this, and has created the new Virtual Robots competi- tion to complement its existing physical robot and agent competitions. In order to successfully compete in this competition, teams need to field multi-robot solutions that cooperatively explore a...

Thanks to advances in both computer science and engineering, the divide between robotics and multi-agent systems is shrinking. Robots are capable of performing an ever wider range of tasks, and there is an increasing need for solutions to high-level problems such as multi-agent coordination. In this paper we examine the problem of finding a robust...

This paper presents the map evaluation methodology developed for the Virtual Robots Rescue competition held as part of RoboCup. The procedure aims to evaluate the quality of maps produced by multi-robot systems with respect to a number of factors, including usability, exploration, annotation and other aspects relevant to robots and first responders...

The 2009 RoboCup Competitions took place in Graz Austria in July of 2009. The Virtual Robot Rescue Competition included 11 competitors from 10 different countries. The main objective of this competition is to utilize teams of robots to perform an urban search and rescue (USAR) mission over both indoor and outdoor terrains. For the first time, eleme...

In this paper we describe a new approach to make use of a heterogeneous robot team for the RoboCup Rescue League Virtual Robot competition. We will demonstrate coordinated action between a flying and a ground robot. The flying robot is used for fast exploration and allows the operator to find the places where victims are present in the environment....

Localization is one of the most important basic skills of a mobile robot. Most approaches, however, still rely either on special sensors or require artificial environments. In this article, a novel approach is presented that can provide compass information for localization, purely based on the visual appearance of a room. A robot using such a visua...

Free space detection based on visual clues is an upcoming approach in robotics. Our working domain is the Virtual Rescue League of the RoboCup. In this domain efficient obstacle avoidance is crucial to find victims under challenging conditions. In this study a machine-learning approach is applied to distinguish the difference in visual appearance o...

This article investigates the prerequisites for a global exploration strategy in an unknown environment on a virtual disaster site. Assume that a robot equipped with a laser range scanner can build a detailed map of a previous unknown environment. The remaining question is how to use this information on this map for further exploration. On a map s...

Omnidirectional vision is currently an important sensor in robotic research. The catadioptric omnidirectional camera with a hyperbolic convex mirror is a common omnidirectional vision system in the robotics research field as it has many advantages over other vision systems. This paper describes the development and validation of such a system for th...

This article investigates the effect of incorporating knowledge about the communication possibilities in an exploration algorithm used to map an unknown environment. The mission is to explore a hypothetical disaster site with a small team of robots. The challenge faced by the robot team is to coordinate their actions such that they efficiently expl...

The capability to follow a person in a domestic environment is an important prerequisite for a robot companion. In this paper, a tracking algorithm is presented that makes it possible to follow a person using a small robot. This algorithm can track a person while moving around, regardless of the sometimes erratic movements of the legged robot. Robu...

Human interaction knows many non-verbal aspects. The use of space, among others, is guided by social rules. Not conforming to these rules may cause discomfort or even mis- communication. If robots are to interact with people, they must follow similar rules. The current work tries to identify factors that influence human preferred interaction distan...

Omnidirectional vision is currently an important sensor in robotic research. The catadioptric omnidirectional camera with a hyperbolic convex mirror is a common omnidirectional vision system in the robotics research field as it has many advantages over other vision systems. This paper describes the development and validation of such a system for th...

This article investigates the scenario where a small team of robots needs to explore a hypothetical disaster site. The challenge faced by the robot-team is to coordinate their actions such that they efficiently explore the environment in their search for victims. A popular paradigm for the exploration problem is based on the notion of frontiers: th...

Published on CD-ROM

Urban Search and Rescue is a growing area of robotic research. The RoboCup Federation has recognized this, and has created the new Virtual Robots competition to complement its existing physical robot and agent competitions. In order to successfully compete in this competition, teams need to field multi-robot solutions that cooperatively explore and...

Recent successful SLAM methods employ hybrid map rep- resentations combining the strengths of topological maps and occupancy grids. Such representations often facilitate multi-agent mapping. In this paper, a successful SLAM method is presented, which is inspired by the manifold data structure by Howard et al. This method maintains a graph with sens...

This discussion paper highlights the design decisions of the UvA Rescue Team on the challenges imposed by the 2007 competition. Consistent with the approach of the previous year, the UvA Rescue Team research focus is dedicated to perceptional issues, to allow later extensions towards complex multi-agent exploration. The Simultaneous Localization an...

The abilities of mobile robots depend greatly on the per- formance of basic skills such as vision and localization. Although great progress has been made in the 4-Legged league in the past years, the performance of many of those approaches completely depends on the artificial environment conditions established on a 4-Legged soccer field. In this ar...

The abilities of mobile robots depend greatly on the performance of basic skills such as vision and localization. Although great progress has been made in the 4-Legged league in the past years, the performance of many of those approaches completely depends on the artificial environment conditions established on a 4-Legged soccer field. In this arti...

The abilities of mobile robots depend greatly on the performance of basic skills such as vision and localization. Although great progress has been made to explore and map extensive public areas with large holonomic robots on wheels, less attention is paid on the localization of a small robot companion in a confined environment as a room in office o...

In this report we describe the algorithms implemented by the Dutch Team in the Sony 4-Legged League. In particular, we describe the new modules on the Aibo side (self-localization, role switching poli- cies, vision) as well as some useful tools we created for the developer side (storing binary snapshots, improved color table creation and perfor- ma...

Designers of autonomous systems, embodied in an uncertain environment, have the ten- dency to build up a world model from everything that can be perceived. In contrast to this view, psychological researchers flnd for humans a selective interpretation of a scene, with phenom- ena like inattentional blindness. Objects remain unseen if they are not ce...

The Dutch AIBO Team is a multi-institute team which competes in the 4-legged robot league of RoboCup since 2004. Our team combines serious research with serious fun: collaborative autonomous (intelligent) systems are applied in Soccer, our shared application domain. This team description paper briefly outlines our current activities for RoboCup 200...

At the end of 2003, several institutes in the Netherlands have joined forces and formed the Dutch AIBO Team. We are a group of researchers and students from the DECIS Lab and the universities of Amsterdam, Delft, Twente and Utrecht. Our goal is to stimulate research, teaching, and applications in the fields of artificial intelligence and collaborat...